© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44198
    Prev
    Next
    INDEX
    Explanations

    SQL queries

    np_max-act · gemini-2.0-flash

    The neuron activates on SQL query syntax elements (e.g. SELECT, FROM, WHERE, JOIN, GROUP BY, ORDER BY).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mob
    -0.07
    orpion
    -0.07
     cripp
    -0.06
     Mozart
    -0.06
     '".
    -0.06
     Unreal
    -0.06
     cmap
    -0.06
    rypt
    -0.06
     PLL
    -0.06
    _Id
    -0.06
    POSITIVE LOGITS
     Various
    0.07
    �
    0.06
     Everyone
    0.06
     Provided
    0.06
     overposting
    0.06
    _OCCURRED
    0.06
     당시
    0.06
     everybody
    0.06
     ever
    0.06
     зберіг
    0.06
    Activations Density 0.005%

    No Known Activations